CN117574280B - Sowing quality detection method based on multivariate characteristic parameters and MDBO-RF - Google Patents
Sowing quality detection method based on multivariate characteristic parameters and MDBO-RF Download PDFInfo
- Publication number
- CN117574280B CN117574280B CN202410050860.XA CN202410050860A CN117574280B CN 117574280 B CN117574280 B CN 117574280B CN 202410050860 A CN202410050860 A CN 202410050860A CN 117574280 B CN117574280 B CN 117574280B
- Authority
- CN
- China
- Prior art keywords
- sowing
- mdbo
- server
- data
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000009331 sowing Methods 0.000 title claims abstract description 71
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000012544 monitoring process Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000010899 nucleation Methods 0.000 claims description 42
- 241000254173 Coleoptera Species 0.000 claims description 15
- 210000003608 fece Anatomy 0.000 claims description 15
- 238000010606 normalization Methods 0.000 claims description 9
- 230000002431 foraging effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000000903 blocking effect Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000000739 chaotic effect Effects 0.000 claims description 3
- 239000000428 dust Substances 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000007637 random forest analysis Methods 0.000 description 14
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 230000017448 oviposition Effects 0.000 description 4
- 230000004888 barrier function Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 241001229848 Aphodius granarius Species 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000019637 foraging behavior Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a sowing quality detection method based on multiple characteristic parameters and MDBO-RF, which comprises the steps of collecting pulse signals of different sowing conditions by an infrared photoelectric sensor arranged on a sowing pipe wall, uploading data to a server, extracting characteristic parameters of the pulse signals by the server to construct a dataset, establishing an RF model to train the dataset, optimizing super parameters of the RF model by MDBO algorithm to form MDBO-RF model, transmitting the super parameters to the server to perform characteristic extraction every time the infrared sensor obtains a signal for sowing in real time in the sowing process, inputting the signal into the trained MDBO-RF model to detect sowing quality, and finally feeding back the result to an agricultural machinery sowing monitoring terminal.
Description
Technical Field
The invention relates to the technical field of agricultural machinery sowing detection, in particular to a sowing quality detection method based on multiple characteristic parameters and MDBO-RF.
Background
The quality of sowing can have an important effect on crop yield, and the traditional sowing machine can cause phenomena of sowing missing, multicasting and blocking of the sowing machine due to the complexity of field work. It is particularly important to detect the sowing in real time. The current sowing detection technology mainly comprises the following steps: ① detecting by a photoelectric sensor; ② Detecting by a piezoelectric sensor; ③ detecting by a capacitance sensor; ④ Visual image detection.
Among photoelectric sensor detection techniques, the infrared photoelectric sensing technique is most widely used. The seeding machine is arranged on the wall of a seed sowing pipe, one side emits an infrared signal, the other side detects the intensity of the infrared signal, the light beam is shielded to cause the change of light intensity in the process of falling of seeds, the intensity of a signal received by a receiving end is changed, the signal is modulated and amplified, and finally, the information of falling of seeds is converted into a pulse signal for detecting the seeding quality.
The existing infrared photoelectric detection technology is concentrated in the aspect of hardware design, is slightly insufficient in an optimization program algorithm, is insufficient in detection method, and is not clear in classification when detecting sowing quality, so that a specific sowing adjustment thought cannot be provided in the actual sowing process of the agricultural machinery. In addition, the existing seeding detection scheme only uses the characteristic of high and low levels of pulse signals to carry out seeding detection too much, and enough characteristics cannot be used for accurately reflecting the seeding condition, so that the judgment result is particularly sensitive to abnormal values, and the change of the signal intensity directly affects the detection accuracy. When the detection signal of the infrared photoelectric sensor is interfered by larger noise, the method has lower accuracy and can not provide accurate seeding detection information.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
Therefore, the invention aims to provide a seeding quality detection method based on multiple characteristic parameters and MDBO-RF, which can improve the accuracy of RF on seeding quality detection.
In order to solve the technical problems, according to one aspect of the present invention, the following technical solutions are provided:
A seeding quality detection method based on multivariate characteristic parameters and MDBO-RF, comprising:
S1, collecting pulse signals of different sowing conditions by using an infrared photoelectric sensor arranged on the wall of a seed sowing pipe, uploading data to a server, and extracting characteristic parameters of the pulse signals by using the server to construct a data set;
s2, building an RF model to train a data set, and optimizing super parameters of the RF model by using MDBO algorithm to form a MDBO-RF model;
and S3, in the sowing process, transmitting the signals to a server for feature extraction every time the infrared sensor acquires the signals for sowing in real time, inputting the signals into a trained MDBO-RF model to detect sowing quality, and finally feeding back the result to an agricultural machinery sowing monitoring terminal.
As a preferred scheme of the seeding quality detection method based on the multivariate characteristic parameters and MDBO-RF, in the step S1, the infrared photoelectric sensors arranged on the seeding pipe wall collect pulse signals under different seeding conditions, the data are uploaded to a server, and the server extracts the characteristic parameters of the pulse signals to construct a data set, wherein the steps are as follows:
respectively collecting pulse signals when the broadcast is missed, the multicast is blocked, the broadcast is normal and the broadcast is influenced by dust by utilizing an infrared photoelectric sensor according to fixed time intervals, and transmitting data to a server;
the server cleans the data, and extracts and processes the multiple characteristic parameters of the pulse signals under different sowing conditions.
As a preferred scheme of the seeding quality detection method based on the multiple characteristic parameters and MDBO-RF, the method for extracting and processing the multiple characteristic parameters of the pulse signals under different seeding conditions comprises the following steps:
Respectively calculating the pulse amplitude Um, pulse width tw, pulse repetition period t, duty factor q, pulse frequency f, pulse energy and the change times of high and low levels generated under different sowing conditions;
Extracting variance and standard deviation of pulse signals in a data acquisition time period;
The method comprises the steps of setting tags for the seeding quality of miss seeding, multicast, blocking, normal seeding and dust-affected seeding quality to classify the seeding quality;
And carrying out Min-Max normalization on the processed data, wherein the normalization formula is as follows, and the Min-Max normalization is used as final model training data:
；
Wherein, the liquid crystal display device comprises a liquid crystal display device, Is a normalized value,/> Is the original data value,/> And/> Respectively, the minimum and maximum of the data.
As a preferable scheme of the seeding quality detection method based on the multivariate characteristic parameters and MDBO-RF, the method for optimizing the hyper-parameters of the RF model by using the MDBO algorithm comprises the following steps:
the population is initialized by using Logistic-tent chaotic mapping, and the formula is as follows:
；
In the middle of Real number representing value range [0,4 ]/> Initial values of system variables;
Calculating the fitness of the current population position;
Updating the position of the dung beetles and carrying out reverse learning when foraging;
And updating the current optimal position and the optimal fitness, sequentially iterating until the maximum iteration times are reached, and outputting an optimal solution.
As a preferred scheme of the seeding quality detection method based on the multivariate characteristic parameters and MDBO-RF, the method comprises the steps of transmitting the signals to a server for characteristic extraction every time an infrared sensor acquires the signals for real-time seeding in the seeding process, inputting the signals into a trained MDBO-RF model for detecting the seeding quality, and finally feeding the results back to an agricultural machinery seeding monitoring terminal, wherein the steps are as follows:
When the agricultural machinery is used for sowing, the infrared sensor is used for collecting sowing signal data according to fixed time intervals, transmitting the data to the server in real time, extracting the same characteristics as training data by the server and inputting the same characteristics into a trained MDBO-RF model, n decision trees can generate n classification results for one input data set, the largest voting frequency is selected in a voting mode to be used as a final sowing quality detection result, and finally, the judgment result is fed back to the sowing monitoring terminal.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, the sowing quality signal data is collected through the infrared photoelectric sensor, more characteristic parameters are extracted, the dependence on single characteristics of the signal data is reduced, so that the sowing quality is more carefully judged, the accuracy of a result is enhanced, and an adjustment scheme can be provided for sowing of agricultural machinery. The MDBO-RF classification algorithm adopted by the invention improves the generalization capability of classification by utilizing the mode of an RF integrated classifier, and simultaneously, the super-parameters of the RF are adaptively adjusted by utilizing the MDBO algorithm according to training data, so that the accuracy of the RF on sowing quality detection can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following detailed description will be given with reference to the accompanying drawings and detailed embodiments, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained from these drawings without inventive faculty for a person skilled in the art. Wherein:
FIG. 1 is a flow chart of a seeding quality detection method based on multiple characteristic parameters and MDBO-RF according to the present invention;
FIG. 2 is a flow chart of MDBO of the seeding quality detection method based on multivariate characterization parameters and MDBO-RF of the present invention;
FIG. 3 is a flow chart of classification of the seeding quality detection method based on the multivariate characteristic parameters and MDBO-RF of the present invention.
Detailed Description
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to the appended drawings.
Next, the present invention will be described in detail with reference to the drawings, wherein the sectional view of the device structure is not partially enlarged to general scale for the convenience of description, and the drawings are only examples, which should not limit the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
The invention provides a seeding quality detection method based on multiple characteristic parameters and MDBO-RF, which can improve the accuracy of the RF on the seeding quality detection.
The invention provides a seeding quality detection algorithm based on multiple characteristic parameters and MDBO-RF, which comprises the steps of firstly, collecting pulse signals of different seeding conditions by an infrared photoelectric sensor arranged on a seeding pipe wall, uploading data to a server, and extracting characteristic parameters of the pulse signals by the server to construct a data set; then, an RF model is built to train the data set, and the super parameters of the RF model are optimized by MDBO algorithm, finally the MDBO-RF model is formed. And in the actual sowing process, the signals obtained by the infrared sensor in real time are transmitted to a server for feature extraction, the signals are input into a trained MDBO-RF model to detect sowing quality, and finally the result is fed back to an agricultural machinery sowing monitoring terminal. The seeding quality detection flow chart is shown in fig. 1.
The specific model training comprises the following steps:
Step1: data collection
Pulse signals when the broadcast is missed, multicast, blocked, normal and affected by dust are respectively collected by utilizing an infrared photoelectric sensor according to fixed time intervals, and data are transmitted to a server.
Step2: feature extraction
The server cleans the data, and extracts and processes the multiple characteristic parameters of the pulse signals under different sowing conditions respectively:
1. The pulse amplitude Um, pulse width tw, pulse repetition period t, duty factor q (q=tw/t), pulse frequency f, pulse energy, and the number of changes in the high and low levels, which are generated in different sowing cases, are calculated, respectively.
2. And extracting the variance and standard deviation of the pulse signals in the data acquisition time period.
3. Tags such as 0,1,2,3,4 are set for several kinds of sowing quality, i.e., miss-seeding, multicast, blocking, normal and dust-affected, to classify sowing quality, e.g., 0 represents miss-seeding.
4. And carrying out Min-Max normalization on the processed data, wherein the normalization formula is as follows, and the Min-Max normalization is used as final model training data:
（1）
Wherein, the liquid crystal display device comprises a liquid crystal display device, Is a normalized value,/> Is the original data value,/> And/> Respectively, the minimum and maximum of the data.
Step3: construction MDBO-RF model
1. The Random Forest (RF) is a classifier algorithm based on Bagging integrated learning, the basic unit is a decision tree, a large number of super parameters exist, the influence of the selection of the number n_ estimators of the decision tree and the maximum depth max_depth of the decision tree on the classification accuracy of the RF is obvious, and if a model is too small, the two parameters can be under fitted, so that the accuracy is poor; if too large, the model will become more complex, resulting in overfitting. Therefore, in order to make the model more fit with data and improve the accuracy of the model on sowing quality classification, the invention uses an improved dung beetle algorithm (DBO) to carry out iterative optimization on the RF super parameters n_ estimators and max_depth. The fitness function is:
（2）
In the middle of for the accuracy of classification,/> The calculation formula is as follows:
（3）
（4）
wherein Exactly is the number of correctly classified samples, total is the Total number of samples. And/> The accuracy and recall rate of the model are respectively calculated according to the following formula:
（5）
（6）
Refers to a positive class sample predicted as a positive class,/> Refers to a negative class sample predicted as a positive class,/> Refers to a negative class sample predicted to be a negative class.
2. The dung beetle algorithm (DBO) is used for optimizing by simulating rolling balls, propagation, foraging and theft of dung beetles in nature.
① Ball behavior
Two different modes are exhibited: the method comprises the steps of having a barrier mode and a barrier-free mode, wherein when the barrier is not present, the intensity of a solar light source can influence the position of a dung beetle, and the position update in the rolling ball process in the barrier mode is shown as a formula (7); when the position of the dung beetle is changed in a dancing way, the position of the dung beetle is updated as shown in a formula (8).
（7）
（8）
In the middle of For/> the dung beetle is at the/> the position at the time of the iteration; /(I) the natural coefficient is zero, no deviation is shown when the value is 1, and the deviation is shown in the original direction when the value is-1; /(I) For deflection coefficient, the value range is/> ;/> Is a value of/> a constant therebetween; /(I) For the worst position of dung beetles,/> For simulating variations in light intensity; /(I) Is a value of/> Deflection angle between, when/> Or/> And when the dung beetles are positioned, the positions of the dung beetles are not updated.
② Propagation behavior
Simulating a safe oviposition area of the dung beetles by using a boundary strategy, wherein the safe oviposition area is shown as a formula (9); once the oviposition area is determined, female dung beetles will produce an egg ball in each iteration, and the position of the egg ball will be dynamically updated as the oviposition area changes, as shown in equation (10).
（9）
（10）
In the middle of Expressed as the current local best position; /(I) And/> Respectively expressed as a lower bound and an upper bound of the spawning area;
,/> The maximum iteration number; /(I) And/> Represented as a lower bound and an upper bound, respectively, of the optimization problem; /(I) For/> Individual egg spheres at the/> Position information at the time of iteration; /(I) And/> Representing two independent random variables of size 1 x D, D representing the dimension of the optimization problem.
③ Foraging behavior
The small dung beetle foraging represents the optimal foraging area and position change through the formula (11) and the formula (12).
（11）
（12）
In the middle of And/> A lower bound and an upper bound representing an optimal foraging area; /(I) representing a global optimal position; /(I) To obey normal distribution of random numbers,/> Is a random vector in the range of (0, 1); /(I) For/> Only small dung beetles are at the/> The position at the time of the iteration.
④ Theft behavior
In the population, thieves will steal food from other dung beetles, and the position update is shown in formula (13).
（13）
In the middle of Is constant,/> The size to obey normal distribution is/> Is a random vector of (c).
To enhance the diversity and uniformity of the initializing population, a Logistic-tent chaotic map is introduced to initialize the population, and the formula is as follows:
（14）
In the middle of Real number representing value range [0,4 ]/> Is the initial value of the system variable.
In order to avoid sinking into local optimum, a reverse learning strategy is introduced in foraging behavior, and the fitness of the foraging position after reverse learning and the original foraging position is compared to select a better solution, wherein the formula is as follows:
（15）
In the middle of And/> Is the upper and lower bounds of the D-dimensional vector,/> Is a D-dimensional random variable. In summary, MDBO is shown in FIG. 2.
Step4: model application
When the agricultural machinery is used for sowing, the infrared sensor is used for collecting sowing signal data according to fixed time intervals, transmitting the data to the server in real time, extracting the same characteristics as training data by the server and inputting the same characteristics into a trained MDBO-RF model, n decision trees can generate n classification results for one input data set, the largest voting frequency is selected in a voting mode to be used as a final sowing quality detection result, and finally, the judgment result is fed back to the sowing monitoring terminal. The classification flow chart is shown in fig. 3.
Although the invention has been described hereinabove with reference to embodiments, various modifications thereof may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In particular, the features of the disclosed embodiments may be combined with each other in any manner as long as there is no structural conflict, and the exhaustive description of these combinations is not given in this specification merely for the sake of omitting the descriptions and saving resources. Therefore, it is intended that the invention not be limited to the particular embodiment disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (3)
1. A seeding quality detection method based on a plurality of characteristic parameters and MDBO-RF, which is characterized by comprising the following steps:
S1, collecting pulse signals of different sowing conditions by using an infrared photoelectric sensor arranged on the wall of a seed sowing pipe, uploading data to a server, and extracting characteristic parameters of the pulse signals by using the server to construct a data set;
s2, building an RF model to train a data set, and optimizing super parameters of the RF model by using MDBO algorithm to form a MDBO-RF model;
S3, in the sowing process, transmitting the sowing signals to a server for feature extraction every time when the infrared sensor obtains the real-time sowing signals, inputting the sowing signals into a trained MDBO-RF model to detect sowing quality, and finally feeding back the result to an agricultural machinery sowing monitoring terminal;
In the step S1, the infrared photoelectric sensor installed on the wall of the seed metering pipe is used to collect pulse signals under different sowing conditions, and upload data to the server, and the server is used to extract characteristic parameters of the pulse signals to construct a data set, which comprises the following steps:
respectively collecting pulse signals when the broadcast is missed, the multicast is blocked, the broadcast is normal and the broadcast is influenced by dust by utilizing an infrared photoelectric sensor according to fixed time intervals, and transmitting data to a server;
the server cleans the data, and extracts and processes the multiple characteristic parameters of the pulse signals under different sowing conditions;
The method for extracting and processing the multiple characteristic parameters of the pulse signals under different sowing conditions comprises the following steps:
Respectively calculating the pulse amplitude Um, pulse width tw, pulse repetition period t, duty factor q, pulse frequency f, pulse energy and the change times of high and low levels generated under different sowing conditions;
Extracting variance and standard deviation of pulse signals in a data acquisition time period;
The method comprises the steps of setting tags for the seeding quality of miss seeding, multicast, blocking, normal seeding and dust-affected seeding quality to classify the seeding quality;
And carrying out Min-Max normalization on the extracted multielement characteristic parameters, wherein the normalization formula is as follows, and the Min-Max normalization is used as final model training data:
wherein X is nom Is normalized value, X is the original data value, X minAnd X max Respectively, the maximum and minimum of the data.
2. The method for detecting sowing quality based on multivariate characteristic parameters and MDBO-RF according to claim 1, wherein the step of optimizing the hyper-parameters of the RF model by MDBO algorithm is as follows:
the population is initialized by using Logistic-tent chaotic mapping, and the formula is as follows:
Wherein u represents a real number in a value range [0,4], and x is an initial value of a system variable;
Calculating the fitness of the current population position;
Updating the position of the dung beetles and carrying out reverse learning when foraging;
And updating the current optimal position and the optimal fitness, sequentially iterating until the maximum iteration times are reached, and outputting an optimal solution.
3. The method for detecting the sowing quality based on the multivariate characteristic parameters and MDBO-RF according to claim 1, wherein in the sowing process, the method is characterized in that the method is transmitted to a server for characteristic extraction every time the infrared sensor obtains a signal for sowing in real time, the signal is input into a trained MDBO-RF model for detecting the sowing quality, and finally the result is fed back to an agricultural machine sowing monitoring terminal as follows:
When the agricultural machinery is used for sowing, the infrared sensor is used for collecting sowing signal data according to fixed time intervals, transmitting the data to the server in real time, extracting the same characteristics as training data by the server and inputting the same characteristics into a trained DBO-RF model, n decision trees can generate n classification results for one input data set, the largest voting frequency is selected in a voting mode to be used as a final sowing quality detection result, and finally, the judgment result is fed back to the sowing monitoring terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410050860.XA CN117574280B (en) | 2024-01-15 | 2024-01-15 | Sowing quality detection method based on multivariate characteristic parameters and MDBO-RF |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410050860.XA CN117574280B (en) | 2024-01-15 | 2024-01-15 | Sowing quality detection method based on multivariate characteristic parameters and MDBO-RF |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117574280A CN117574280A (en) | 2024-02-20 |
| CN117574280B true CN117574280B (en) | 2024-04-16 |
Family
ID=89884814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410050860.XA Active CN117574280B (en) | 2024-01-15 | 2024-01-15 | Sowing quality detection method based on multivariate characteristic parameters and MDBO-RF |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117574280B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102968079A (en) * | 2012-10-31 | 2013-03-13 | 长春理工大学 | Seeding monitoring system of corn precision seeder |
| CN203149368U (en) * | 2013-03-04 | 2013-08-21 | 北京农业智能装备技术研究中心 | Seeding condition monitoring equipment for corn precision seeder |
| CN104392430A (en) * | 2014-10-22 | 2015-03-04 | 华南农业大学 | Machine vision-based super hybrid rice bunch seeding quantity detection method and device |
| CN106134579A (en) * | 2015-04-03 | 2016-11-23 | 中国农业机械化科学研究院 | Pneumatic precision planting with sowing machine monitoring device and monitoring method |
| CN107409547A (en) * | 2017-06-02 | 2017-12-01 | 南京农业大学 | A kind of intelligent seeding operation system based on big-dipper satellite |
| CN108801665A (en) * | 2018-03-27 | 2018-11-13 | 昆明理工大学 | A kind of no-till maize mass monitoring system based on LabVIEW |
| CN109660297A (en) * | 2018-12-19 | 2019-04-19 | 中国矿业大学 | A kind of physical layer visible light communication method based on machine learning |
| CN114694047A (en) * | 2022-04-12 | 2022-07-01 | 中国农业科学院作物科学研究所 | Corn sowing quality evaluation method and device |
| CN116451142A (en) * | 2023-06-09 | 2023-07-18 | 山东云泷水务环境科技有限公司 | Water quality sensor fault detection method based on machine learning algorithm |
| CN116453162A (en) * | 2023-04-13 | 2023-07-18 | 天津农学院 | Dorking health state identification method based on dung beetle optimization algorithm |
| CN116671318A (en) * | 2023-08-02 | 2023-09-01 | 南京农业大学 | Intelligent monitoring and positioning marking system and method for seed discharging performance of garlic planter |
| CN116702053A (en) * | 2023-08-09 | 2023-09-05 | 长春理工大学 | Agricultural machinery fault detection method based on multiple information and MCSA-SVM |
| CN116910542A (en) * | 2023-06-30 | 2023-10-20 | 淮阴工学院 | Exhaust pollution prediction method based on improved dung beetle algorithm for optimizing Elman neural network |
| CN117332340A (en) * | 2023-10-24 | 2024-01-02 | 长安大学 | PMSM fault diagnosis method and system based on multi-sensor visual feature fusion |
| CN117370877A (en) * | 2023-12-06 | 2024-01-09 | 长春理工大学 | Agricultural machinery fault prediction method based on multiple sensors and IPSO-GPR |
| CN117392157A (en) * | 2023-12-13 | 2024-01-12 | 长春理工大学 | Edge-aware protective cultivation straw coverage rate detection method |
-
2024
- 2024-01-15 CN CN202410050860.XA patent/CN117574280B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102968079A (en) * | 2012-10-31 | 2013-03-13 | 长春理工大学 | Seeding monitoring system of corn precision seeder |
| CN203149368U (en) * | 2013-03-04 | 2013-08-21 | 北京农业智能装备技术研究中心 | Seeding condition monitoring equipment for corn precision seeder |
| CN104392430A (en) * | 2014-10-22 | 2015-03-04 | 华南农业大学 | Machine vision-based super hybrid rice bunch seeding quantity detection method and device |
| CN106134579A (en) * | 2015-04-03 | 2016-11-23 | 中国农业机械化科学研究院 | Pneumatic precision planting with sowing machine monitoring device and monitoring method |
| CN107409547A (en) * | 2017-06-02 | 2017-12-01 | 南京农业大学 | A kind of intelligent seeding operation system based on big-dipper satellite |
| CN108801665A (en) * | 2018-03-27 | 2018-11-13 | 昆明理工大学 | A kind of no-till maize mass monitoring system based on LabVIEW |
| CN109660297A (en) * | 2018-12-19 | 2019-04-19 | 中国矿业大学 | A kind of physical layer visible light communication method based on machine learning |
| CN114694047A (en) * | 2022-04-12 | 2022-07-01 | 中国农业科学院作物科学研究所 | Corn sowing quality evaluation method and device |
| CN116453162A (en) * | 2023-04-13 | 2023-07-18 | 天津农学院 | Dorking health state identification method based on dung beetle optimization algorithm |
| CN116451142A (en) * | 2023-06-09 | 2023-07-18 | 山东云泷水务环境科技有限公司 | Water quality sensor fault detection method based on machine learning algorithm |
| CN116910542A (en) * | 2023-06-30 | 2023-10-20 | 淮阴工学院 | Exhaust pollution prediction method based on improved dung beetle algorithm for optimizing Elman neural network |
| CN116671318A (en) * | 2023-08-02 | 2023-09-01 | 南京农业大学 | Intelligent monitoring and positioning marking system and method for seed discharging performance of garlic planter |
| CN116702053A (en) * | 2023-08-09 | 2023-09-05 | 长春理工大学 | Agricultural machinery fault detection method based on multiple information and MCSA-SVM |
| CN117332340A (en) * | 2023-10-24 | 2024-01-02 | 长安大学 | PMSM fault diagnosis method and system based on multi-sensor visual feature fusion |
| CN117370877A (en) * | 2023-12-06 | 2024-01-09 | 长春理工大学 | Agricultural machinery fault prediction method based on multiple sensors and IPSO-GPR |
| CN117392157A (en) * | 2023-12-13 | 2024-01-12 | 长春理工大学 | Edge-aware protective cultivation straw coverage rate detection method |
Non-Patent Citations (3)
| Title |
|---|
| 基于改进灰狼算法和自适应***KD-Tree 的点云配准方法;杜沅昊 等;《***仿真学报》;20231207;第1.2.1节 * |
| 多策略改进的蜣螂优化算法及其应用;郭琴 等;《计算机科学与探索》;20231215;全文 * |
| 新型玉米精密播种机排种监视器设计;杨宏伟 等;《长春理工大学学报（自然科学版）》;20150430;第38卷(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117574280A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180070527A1 (en) | Systems for learning farmable zones, and related methods and apparatus | |
| Wang et al. | YOLOv3‐Litchi Detection Method of Densely Distributed Litchi in Large Vision Scenes | |
| Devi et al. | IoT enabled efficient detection and classification of plant diseases for agricultural applications | |
| CN104766099B (en) | Distribution type fiber-optic circumference vibration signal processing and recognition methods based on image | |
| CN110765916A (en) | Farmland seedling ridge identification method and system based on semantics and example segmentation | |
| CN111723711A (en) | Plianes and object-oriented mulching film information extraction method and system | |
| Xie et al. | Research on carrot grading based on machine vision feature parameters | |
| Guillén-Navarro et al. | A deep learning model to predict lower temperatures in agriculture | |
| CN115220007A (en) | Radar point cloud data enhancement method aiming at attitude identification | |
| CN117574280B (en) | Sowing quality detection method based on multivariate characteristic parameters and MDBO-RF | |
| CN111723712A (en) | Method and system for extracting mulching film information based on radar remote sensing data and object-oriented mulching film information | |
| Sunil et al. | A review on prediction of crop yield using machine learning techniques | |
| Kundur et al. | Deep convolutional neural network architecture for plant seedling classification | |
| CN103971362B (en) | SAR image change-detection based on rectangular histogram and elite genetic algorithm for clustering | |
| Paudel et al. | Prediction of crop yield based-on soil moisture using machine learning algorithms | |
| Wang et al. | Accurate detection and precision spraying of corn and weeds using the improved YOLOv5 model | |
| Abdulla et al. | Agriculture based on internet of things and deep learning | |
| Sudha et al. | Real time riped fruit detection using faster R-CNN deep neural network models | |
| Kang et al. | Research on an improved YOLOv8 image segmentation model for crop pests | |
| Gai et al. | Cherry detection algorithm based on improved YOLOv5s network | |
| Sethy et al. | Pest detection and recognition in rice crop using svm in approach of bag-of-words | |
| CN112364710A (en) | Plant electric signal classification and identification method based on deep learning algorithm | |
| Xie et al. | A signal output quantity (SOQ) judgment algorithm for improving seeding quantity accuracy | |
| Karuna et al. | Convolutional and spiking neural network models for crop yield forecasting | |
| CN115392311A (en) | Efficient sugarcane stalk node identification method based on variational modal decomposition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |